CN110033768A - A kind of method and apparatus of intelligent search spokesman - Google Patents
A kind of method and apparatus of intelligent search spokesman Download PDFInfo
- Publication number
- CN110033768A CN110033768A CN201910322936.9A CN201910322936A CN110033768A CN 110033768 A CN110033768 A CN 110033768A CN 201910322936 A CN201910322936 A CN 201910322936A CN 110033768 A CN110033768 A CN 110033768A
- Authority
- CN
- China
- Prior art keywords
- data
- spokesman
- voice
- audio processor
- processor
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08C—TRANSMISSION SYSTEMS FOR MEASURED VALUES, CONTROL OR SIMILAR SIGNALS
- G08C17/00—Arrangements for transmitting signals characterised by the use of a wireless electrical link
- G08C17/02—Arrangements for transmitting signals characterised by the use of a wireless electrical link using a radio link
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/54—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for retrieval
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/80—Services using short range communication, e.g. near-field communication [NFC], radio-frequency identification [RFID] or low energy communication
Abstract
The invention discloses the method and apparatus of intelligent search spokesman a kind of, including audio processor, one end insertion of the audio processor is equipped with control panel, the other end of the audio processor is symmetrically installed with lifting handle, structure of the invention is scientific and reasonable, it is safe and convenient to use, when spokesman makes a speech, it is acquired by voice data of the sound pick-up to spokesman, and voice data is analyzed and processed by data processor, then collected voice tamber data and speech text data are transmitted in cloud database by GPRS data transmitter, it compares, speech text data comparison result and voice tamber data comparing result are compared, if identical, then export comparing result, if comparing result is different, then the spokesman's voice data received is analyzed and processed by data processor again, Voice tamber data and speech text data are resolved into, and carries out networking comparison again.
Description
Technical field
The present invention relates to technical field of voice recognition, specially a kind of method and apparatus of intelligent search spokesman.
Background technique
In modern establishment and family, audio-video conferencing has become very universal, in audio-video conferencing
In, when spokesman is in speech, people are often desirable to obtain the image or identity information of spokesman, particularly with video conference
Speech, highlights the video information of spokesman on meeting-place, enables to video conference to have similar with face-to-face meetings existing
Field impression, also, recording event by electronic equipment recording audio or recorded video at present is that daily life is brought greatly
Convenience, such as: on classroom teacher's lecture content carry out audio-video recording, facilitate teacher impart knowledge to students again or student review function
Class；Alternatively, being provided in occasions such as meeting, viewing live telecasts using the convenient broadcasting again of electronic equipment recording audio/video or electronics
The archive of material is consulted etc.；
It, cannot only root for unfamiliar people or sound however, when there is more human hairs speech in audio-video document or video conference
It is the information for identifying current speaker or all spokesman according to face or sound, or when needing to form committee paper, also
It needs artificially to play back and records and voluntarily distinguish that sound just can recognize that the corresponding spokesman of each audio, if comparing footpath between fields to spokesman
It survives and is extremely easy to appear situations such as identification is wrong, influence the identification and acquisition of spokesman's voice data.
Summary of the invention
The present invention provides a kind of technical solution, can effectively solve it is mentioned above in the background art when audio-video document or
It is that unfamiliar people or sound cannot be identified according only to face or sound current when having more human hairs speech in video conference
The information of spokesman or all spokesman, or when needing to form committee paper, it is also necessary to artificial playback is recorded and is voluntarily distinguished
Other sound just can recognize that the corresponding spokesman of each audio, if stranger to spokesman be also extremely easy to appear identification mistake
Situations such as, the problem of influencing the identification and acquisition of spokesman's voice data.
To achieve the above object, the invention provides the following technical scheme: a kind of intelligent search spokesman equipment, including audio
One end insertion of processor, the audio processor is equipped with control panel, and the other end of the audio processor is symmetrically installed
There is lifting handle；
One end insertion of the audio processor is equipped with antenna accommodating mechanism, and the antenna accommodating mechanism includes shifting chute, lid
Plate, guide rail, antenna, collect slot, fixing axle, plane scroll spring, electric wire and collect roller and electric wire the block that is slidably installed；
One end of the audio processor offers shifting chute, and one end of the shifting chute is rotatably connected to cover board, the movement
The both ends inner wall of slot is symmetrically connected with guide rail, slidably connects the block that is slidably installed between two guide rails, described to be slidably installed
One end of block is rotatably equipped with antenna, and the inside of the audio processor, which corresponds to offer at one side position of shifting chute, collects slot,
One end inner wall for collecting slot is rotatably equipped with fixing axle, and plane scroll spring is connected on the outside of the fixing axle, described
One end connection live wire of plane scroll spring collects roller, and the electric wire collects the outside connection live wire of roller.
According to above-mentioned technical characteristic, antirusting paint, the outside packet of the lifting handle are coated on the outside of the audio processor
It is covered with non-slip rubber set.
According to above-mentioned technical characteristic, the inner wall of the audio processor is equipped with GPRS data transmitter, at the audio
The inner wall of reason device, which corresponds to, is equipped with data processor at one side position of GPRS data transmitter；
The input terminal of the control panel is electrically connected the output end of alternating current, and the output end of the control panel is electrically connected GPRS
The input terminal of data link and data processor.
According to above-mentioned technical characteristic, one end of the electric wire passes through the block that is slidably installed and connect with antenna, the electric wire it is another
One end is connect with GPRS data transmitter.
A kind of method of intelligent search spokesman, includes the following steps:
S1, phonetic incepting: spokesman's voice data is acquired by sound pick-up；
S2, speech recognition: collected spokesman's voice data is delivered in audio processor, is carried out by data processor
Speech recognition obtains speech text data and voice tamber data；
S3, Speech comparison: collected voice tamber data is delivered in cloud database by GPRS data transmitter, into
Row search comparison；
S4, transcription comparison: collected speech text data are transmitted to internet search engine by GPRS data transmitter
On, it scans for comparing with the text data recorded on internet；
S5, result integration: voice tone color comparing result and speech text comparing result are compared into integration；
S6, data storage: collected voice tamber data and speech text are corresponded into spokesman's identity, are delivered to cloud data
It is stored in library.
According to above-mentioned technical characteristic, spokesman's voice data is acquired by sound pick-up in the step 1, it is described to pick up
The quantity of sound device is three, and the installation site of three sound pick-ups is different, and the installation site of three sound pick-ups can root
It is voluntarily adjusted according to user's demand.
According to above-mentioned technical characteristic, audio conversion text software, the step are mounted in the step 2 sound intermediate frequency processor
Collected voice data can be by Bluetooth wireless transmission to audio processor, by data processor processes at single in 2
Syllable tamber data and the output of speech text data.
According to above-mentioned technical characteristic, the collected voice tamber data of step 2 can be passed through into GPRS data in the step 3
Transmitter is transmitted in cloud database, is compared with the spokesman's voice tamber data stored in cloud database, and defeated
Comparing result out.
According to above-mentioned technical characteristic, in the step 4, collected speech text data can be inputted draws in internet hunt
It in holding up, and is transmitted on internet and is scanned for by GPRS data transmitter, by search result and collected speech text
Data compare, and export comparing result.
According to above-mentioned technical characteristic, in the step 5, voice tamber data comparing result and speech text data comparison knot
Fruit can be delivered in audio processor, be compared by data processor, if comparing result is not identical, then return to step 2,
Analysis processing is re-started to voice data.
Compared with prior art, beneficial effects of the present invention: structure of the invention is scientific and reasonable, safe and convenient to use: the intelligence
Spokesman's equipment can be searched in use, the block that is slidably installed that will drive the connection of antenna one end is mobile, sliding peace by pulling antenna
Dress block meeting follows track moves in shifting chute, and after antenna is all pulled out out of shifting chute, antenna may be reversed, antenna is turned
It moves to state in a vertical shape, when the block that is slidably installed is mobile, the electric wire that will drive block one end connection that is slidably installed is mobile, can drive electric wire
Roller rotation is collected, when electric wire collects roller rotation, will drive plane scroll spring contraction, it, can when audio processor is without the use of
Antenna is turned to and is in a horizontal state by rotary antenna, and the plane scroll spring of contraction can generate rebound, drives electric wire to collect roller anti-
To rotation, electric wire is convergent on electric wire and is collected on roller, when electric wire is convergent on electric wire and collects on roller, electric wire, which will drive, to be slidably installed
Block follows track moves in shifting chute, to drive the antenna for block one end connection that is slidably installed mobile, can be convergent on antenna
In shifting chute, and by cover board, the exit of shifting chute is covered and is protected；
When spokesman makes a speech, it can be acquired, be picked up by voice data of the sound pick-up that multiple and different positions are installed to spokesman
The collected spokesman's voice data of sound device can be delivered in audio processor by bluetooth, and by data processor to reception
To spokesman's voice data be analyzed and processed, spokesman's voice data is resolved into voice tamber data and speech text number
According to then collected voice tamber data being transmitted in cloud database by GPRS data transmitter, with cloud number
It is compared according to the spokesman's voice tamber data stored in library, and exports comparing result, meanwhile, by collected speech text
Data input in internet search engine, and are transmitted on internet and are scanned for by GPRS data transmitter, will search for
As a result it is compared with collected speech text data, and exports comparing result, by speech text data comparison result and language
Sound tamber data comparing result compares, if identical, then exports comparing result, if comparing result is different, then passes through again
Data processor is analyzed and processed the spokesman's voice data received, resolves into voice tamber data and speech text number
According to, and networking comparison is carried out again.
Detailed description of the invention
Attached drawing is used to provide further understanding of the present invention, and constitutes part of specification, with reality of the invention
It applies example to be used to explain the present invention together, not be construed as limiting the invention.
In the accompanying drawings:
Fig. 1 is flow diagram of the invention；
Fig. 2 is structural schematic diagram of the invention；
Fig. 3 is present invention lifting the mounting structure schematic diagram with audio processor；
Fig. 4 is the structural schematic diagram of inventive antenna accommodating mechanism；
Fig. 5 is the mounting structure schematic diagram of GPRS data transmitter and data processor of the present invention；
Figure label: 1, audio processor；2, control panel；3, handle is lifted；
4, antenna accommodating mechanism；401, shifting chute；402, cover board；403, guide rail；404, be slidably installed block；405, antenna；406,
Collect slot；407, fixing axle；408, plane scroll spring；409, electric wire collects roller；410, electric wire；
5, GPRS data transmitter；6, data processor.
Specific embodiment
Hereinafter, preferred embodiments of the present invention will be described with reference to the accompanying drawings, it should be understood that preferred reality described herein
Apply example only for the purpose of illustrating and explaining the present invention and is not intended to limit the present invention.
Embodiment 1: as shown in Figure 2-5, the present invention provides a kind of technical solution, a kind of intelligent search spokesman equipment, packet
Audio processor 1 is included, one end insertion of audio processor 1 is equipped with control panel 2, and the other end of audio processor 1 is symmetrically pacified
Equipped with lifting 3；
One end insertion of audio processor 1 is equipped with antenna accommodating mechanism 4, and antenna accommodating mechanism 4 includes shifting chute 401, cover board
402, guide rail 403, the block 404 that is slidably installed, antenna 405, collect slot 406, fixing axle 407, plane scroll spring 408, electric wire receive
Beam roller 409 and electric wire 410；
One end of audio processor 1 offers shifting chute 401, and one end of shifting chute 401 is rotatably connected to cover board 402, shifting chute
401 both ends inner wall is symmetrically connected with guide rail 403, and the block 404 that is slidably installed, sliding peace are slidably connected between two guide rails 403
One end of dress block 404 is rotatably equipped with antenna 405, and the inside of audio processor 1 corresponds to be offered at 401 1 side position of shifting chute
Slot 406 is collected, one end inner wall for collecting slot 406 is rotatably equipped with fixing axle 407, and the outside of fixing axle 407 is connected with planar vortex
One end connection live wire of coil spring 408, plane scroll spring 408 collects roller 409, and the outside that electric wire collects roller 409 is connected with
Electric wire 410, the outside of audio processor 1 are coated with antirusting paint, and 3 outside is coated with non-slip rubber set, increases sound by lifting
The antirust ability of frequency processor 1.
The inner wall of audio processor 1 is equipped with GPRS data transmitter 5, and the inner wall of audio processor 1 corresponds to GPRS data
Data processor 6 is installed at 5 one side position of transmitter；
The input terminal of control panel 2 is electrically connected the output end of alternating current, and the output end of control panel 2 is electrically connected GPRS data and passes
The input terminal of defeated device 5 and data processor 6, one end of electric wire 410 pass through the block 404 that is slidably installed and connect with antenna 405, electric wire
410 other end is connect with GPRS data transmitter 5, and GPRS data transmitter 5 is connect by electric wire 410 with antenna 405.
The working principle of the invention and process for using: intelligent search spokesman equipment is in use, pull antenna 405, meeting
Drive the block 404 that is slidably installed of 405 one end of antenna connection mobile, the block 404 that is slidably installed meeting follows track 403 is in shifting chute 401
Interior movement after all pulling out antenna 405 out of shifting chute 401, may be reversed antenna 405, antenna 405 turned in vertical
State, when the block 404 that is slidably installed is mobile, the electric wire 410 that will drive 404 one end of block connection that is slidably installed is mobile, can drive electric wire
The rotation of roller 409 is collected, when electric wire collects roller 409 and rotates, will drive the contraction of plane scroll spring 408, audio processor 1 is not required to
In use, rotatable antenna 405, antenna 405 is turned to and is in a horizontal state, the plane scroll spring 408 of contraction can be generated back
Bullet drives electric wire to collect roller 409 and rotates backward, electric wire 410 is convergent on electric wire and is collected on roller 409, is convergent on electricity in electric wire 410
When line is collected on roller 409, electric wire 410 will drive 404 follows track 403 of block that is slidably installed and move in shifting chute 401, thus band
The antenna 405 of dynamic 404 one end of block connection that is slidably installed is mobile, antenna 405 can be convergent in shifting chute 401, and pass through cover board
402, the exit of shifting chute 401 is covered and is protected.
Embodiment 2: as shown in Figs. 1-5, the present invention provides a kind of technical solution, a kind of intelligent search spokesman equipment, packet
Audio processor 1 is included, one end insertion of audio processor 1 is equipped with control panel 2, and the other end of audio processor 1 is symmetrically pacified
Equipped with lifting 3；
One end insertion of audio processor 1 is equipped with antenna accommodating mechanism 4, and antenna accommodating mechanism 4 includes shifting chute 401, cover board
402, guide rail 403, the block 404 that is slidably installed, antenna 405, collect slot 406, fixing axle 407, plane scroll spring 408, electric wire receive
Beam roller 409 and electric wire 410；
One end of audio processor 1 offers shifting chute 401, and one end of shifting chute 401 is rotatably connected to cover board 402, shifting chute
401 both ends inner wall is symmetrically connected with guide rail 403, and the block 404 that is slidably installed, sliding peace are slidably connected between two guide rails 403
One end of dress block 404 is rotatably equipped with antenna 405, and the inside of audio processor 1 corresponds to be offered at 401 1 side position of shifting chute
Slot 406 is collected, one end inner wall for collecting slot 406 is rotatably equipped with fixing axle 407, and the outside of fixing axle 407 is connected with planar vortex
One end connection live wire of coil spring 408, plane scroll spring 408 collects roller 409, and the outside that electric wire collects roller 409 is connected with
Electric wire 410, the outside of audio processor 1 are coated with antirusting paint, and 3 outside is coated with non-slip rubber set, increases sound by lifting
The antirust ability of frequency processor 1.
The inner wall of audio processor 1 is equipped with GPRS data transmitter 5, and the inner wall of audio processor 1 corresponds to GPRS data
Data processor 6 is installed at 5 one side position of transmitter；
The input terminal of control panel 2 is electrically connected the output end of alternating current, and the output end of control panel 2 is electrically connected GPRS data and passes
The input terminal of defeated device 5 and data processor 6, one end of electric wire 410 pass through the block 404 that is slidably installed and connect with antenna 405, electric wire
410 other end is connect with GPRS data transmitter 5, and GPRS data transmitter 5 is connect by electric wire 410 with antenna 405.
A kind of method of intelligent search spokesman, includes the following steps:
S1, phonetic incepting: spokesman's voice data is acquired by sound pick-up；
S2, speech recognition: collected spokesman's voice data is delivered in audio processor 1, by data processor 6 into
Row speech recognition obtains speech text data and voice tamber data；
S3, Speech comparison: collected voice tamber data is delivered in cloud database by GPRS data transmitter 5,
It scans for comparing；
S4, transcription comparison: collected speech text data are transmitted to internet search engine by GPRS data transmitter 5
On, it scans for comparing with the text data recorded on internet；
S5, result integration: voice tone color comparing result and speech text comparing result are compared into integration；
S6, data storage: collected voice tamber data and speech text are corresponded into spokesman's identity, are delivered to cloud data
It is stored in library.
According to above-mentioned technical characteristic, spokesman's voice data is acquired by sound pick-up in step 1, the number of sound pick-up
Amount is three, and the installation site of three sound pick-ups is different, and the installation site of three sound pick-ups can be according to user's demand voluntarily
Adjustment.
According to above-mentioned technical characteristic, it is mounted with audio conversion text software in step 2 sound intermediate frequency processor 1, is acquired in step 2
The voice data arrived can be by being processed into single syllable sound by data processor 6 in Bluetooth wireless transmission to audio processor 1
Chromatic number evidence and the output of speech text data.
According to above-mentioned technical characteristic, the collected voice tamber data of step 2 can be transmitted by GPRS data in step 3
Device 5 is transmitted in cloud database, is compared with the spokesman's voice tamber data stored in cloud database, and output pair
Compare result.
According to above-mentioned technical characteristic, in step 4, collected speech text data can be inputted in internet search engine
It is interior, and be transmitted on internet and scanned for by GPRS data transmitter 5, by search result and collected speech text number
According to comparing, and export comparing result.
According to above-mentioned technical characteristic, in step 5, voice tamber data comparing result and speech text data comparison result meeting
It is delivered in audio processor 1, is compared by data processor 6, if comparing result is not identical, then return to step 2, it is right
Voice data re-starts analysis processing.
The working principle of the invention and process for using: intelligent search spokesman equipment is in use, pull antenna 405, meeting
Drive the block 404 that is slidably installed of 405 one end of antenna connection mobile, the block 404 that is slidably installed meeting follows track 403 is in shifting chute 401
Interior movement after all pulling out antenna 405 out of shifting chute 401, may be reversed antenna 405, antenna 405 turned in vertical
State, when the block 404 that is slidably installed is mobile, the electric wire 410 that will drive 404 one end of block connection that is slidably installed is mobile, can drive electric wire
The rotation of roller 409 is collected, when electric wire collects roller 409 and rotates, will drive the contraction of plane scroll spring 408, audio processor 1 is not required to
In use, rotatable antenna 405, antenna 405 is turned to and is in a horizontal state, the plane scroll spring 408 of contraction can be generated back
Bullet drives electric wire to collect roller 409 and rotates backward, electric wire 410 is convergent on electric wire and is collected on roller 409, is convergent on electricity in electric wire 410
When line is collected on roller 409, electric wire 410 will drive 404 follows track 403 of block that is slidably installed and move in shifting chute 401, thus band
The antenna 405 of dynamic 404 one end of block connection that is slidably installed is mobile, antenna 405 can be convergent in shifting chute 401, and pass through cover board
402, the exit of shifting chute 401 is covered and is protected；
When spokesman makes a speech, it can be acquired, be picked up by voice data of the sound pick-up that multiple and different positions are installed to spokesman
The collected spokesman's voice data of sound device can be delivered in audio processor 1 by bluetooth, and be docked by data processor 6
The spokesman's voice data received is analyzed and processed, and spokesman's voice data is resolved into voice tamber data and speech text
Collected voice tamber data can be then transmitted in cloud database, with cloud by data by GPRS data transmitter 5
Spokesman's voice tamber data of databases storage compares, and exports comparing result, meanwhile, by collected voice text
Notebook data inputs in internet search engine, and is transmitted on internet and is scanned for by GPRS data transmitter 5, will search
Hitch fruit compares with collected speech text data, and exports comparing result, by speech text data comparison result and
Voice tamber data comparing result compares, if identical, then exports comparing result, if comparing result is different, then leads to again
It crosses data processor 6 to be analyzed and processed the spokesman's voice data received, resolves into voice tamber data and voice text
Notebook data, and networking comparison is carried out again.
Finally, it should be noted that being not intended to restrict the invention the foregoing is merely preferred embodiment of the invention, to the greatest extent
Present invention has been described in detail with reference to the aforementioned embodiments for pipe, for those skilled in the art, still can be with
It modifies the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features.It is all
Within the spirit and principles in the present invention, any modification, equivalent replacement, improvement and so on should be included in guarantor of the invention
Within the scope of shield.
Claims (10)
1. a kind of intelligent search spokesman equipment, including audio processor, it is characterised in that: one end of the audio processor is embedding
Enter and control panel is installed, the other end of the audio processor is symmetrically installed with lifting handle；
One end insertion of the audio processor is equipped with antenna accommodating mechanism, and the antenna accommodating mechanism includes shifting chute, lid
Plate, guide rail, antenna, collect slot, fixing axle, plane scroll spring, electric wire and collect roller and electric wire the block that is slidably installed；
One end of the audio processor offers shifting chute, and one end of the shifting chute is rotatably connected to cover board, the movement
The both ends inner wall of slot is symmetrically connected with guide rail, slidably connects the block that is slidably installed between two guide rails, described to be slidably installed
One end of block is rotatably equipped with antenna, and the inside of the audio processor, which corresponds to offer at one side position of shifting chute, collects slot,
One end inner wall for collecting slot is rotatably equipped with fixing axle, and plane scroll spring is connected on the outside of the fixing axle, described
One end connection live wire of plane scroll spring collects roller, and the electric wire collects the outside connection live wire of roller.
2. a kind of intelligent search spokesman equipment according to claim 1, which is characterized in that outside the audio processor
Side is coated with antirusting paint, is coated with non-slip rubber set on the outside of the lifting handle.
3. a kind of intelligent search spokesman equipment according to claim 1, which is characterized in that the audio processor it is interior
Wall is equipped with GPRS data transmitter, and the inner wall of the audio processor corresponds to be equipped at one side position of GPRS data transmitter
Data processor；
The input terminal of the control panel is electrically connected the output end of alternating current, and the output end of the control panel is electrically connected GPRS
The input terminal of data link and data processor.
4. a kind of intelligent search spokesman equipment according to claim 1, which is characterized in that one end of the electric wire passes through
The block that is slidably installed is connect with antenna, and the other end of the electric wire is connect with GPRS data transmitter.
5. the method for intelligent search spokesman according to claim 1-4 a kind of, which is characterized in that including as follows
Step:
S1, phonetic incepting: spokesman's voice data is acquired by sound pick-up；
S2, speech recognition: collected spokesman's voice data is delivered in audio processor, is carried out by data processor
Speech recognition obtains speech text data and voice tamber data；
S3, Speech comparison: collected voice tamber data is delivered in cloud database by GPRS data transmitter, into
Row search comparison；
S4, transcription comparison: collected speech text data are transmitted to internet search engine by GPRS data transmitter
On, it scans for comparing with the text data recorded on internet；
S5, result integration: voice tone color comparing result and speech text comparing result are compared into integration；
S6, data storage: collected voice tamber data and speech text are corresponded into spokesman's identity, are delivered to cloud data
It is stored in library.
6. the method for intelligent search spokesman according to claim 5 a kind of, which is characterized in that pass through in the step 1
Sound pick-up is acquired spokesman's voice data, and the quantity of the sound pick-up is three, the installation position of three sound pick-ups
Difference is set, and the installation site of three sound pick-ups can voluntarily be adjusted according to user's demand.
7. the method for intelligent search spokesman according to claim 5 a kind of, which is characterized in that step 2 sound intermediate frequency
Audio conversion text software is mounted in processor, collected voice data can be by Bluetooth wireless transmission extremely in the step 2
In audio processor, exported by data processor processes at single syllable tamber data and speech text data.
8. the method for intelligent search spokesman according to claim 5 a kind of, which is characterized in that will step in the step 3
Rapid 2 collected voice tamber data can be transmitted in cloud database by GPRS data transmitter, in cloud database
Spokesman's voice tamber data of storage compares, and exports comparing result.
9. the method for intelligent search spokesman according to claim 5 a kind of, which is characterized in that in the step 4, acquisition
To speech text data can input in internet search engine, and it is enterprising by GPRS data transmitter to be transmitted to internet
Row search, search result and collected speech text data is compared, and export comparing result.
10. the method for intelligent search spokesman according to claim 5 a kind of, which is characterized in that in the step 5, language
Sound tamber data comparing result and speech text data comparison result can be delivered in audio processor, by data processor into
Row comparison, if comparing result is not identical, then returns to step 2, re-starts analysis processing to voice data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910322936.9A CN110033768A (en) | 2019-04-22 | 2019-04-22 | A kind of method and apparatus of intelligent search spokesman |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910322936.9A CN110033768A (en) | 2019-04-22 | 2019-04-22 | A kind of method and apparatus of intelligent search spokesman |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110033768A true CN110033768A (en) | 2019-07-19 |
Family
ID=67239381
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910322936.9A Pending CN110033768A (en) | 2019-04-22 | 2019-04-22 | A kind of method and apparatus of intelligent search spokesman |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110033768A (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1291112A (en) * | 1998-12-24 | 2001-04-11 | 索尼公司 | Information processor, portable device, electronic pet device, recorded medium on which information processing procedure is recorded, and information processing method |
| CN1422424A (en) * | 2000-03-02 | 2003-06-04 | 雅马哈株式会社 | Telephone terminal |
| CN201490318U (en) * | 2009-04-27 | 2010-05-26 | 中兴通讯股份有限公司 | Mobile phone and rod antenna |
| CN201838706U (en) * | 2010-10-15 | 2011-05-18 | 福建星海通信科技有限公司 | Telescopic antenna |
| CN105228434A (en) * | 2015-08-13 | 2016-01-06 | 诸爱道 | Security terminal machine |
| CN105789813A (en) * | 2016-03-23 | 2016-07-20 | 广东丰光科技有限公司 | Expansion antenna device |
| CN106919561A (en) * | 2017-04-25 | 2017-07-04 | 安徽声讯信息技术有限公司 | Intelligent meeting stenographic machine |
| CN107221331A (en) * | 2017-06-05 | 2017-09-29 | 深圳市讯联智付网络有限公司 | A kind of personal identification method and equipment based on vocal print |
| CN108399923A (en) * | 2018-02-01 | 2018-08-14 | 深圳市鹰硕技术有限公司 | More human hairs call the turn spokesman's recognition methods and device |
| CN208027740U (en) * | 2018-04-24 | 2018-10-30 | 郑州小蝌蚪文化传播有限公司 | A kind of portable intelligent sound identification device |
| CN108986826A (en) * | 2018-08-14 | 2018-12-11 | 中国平安人寿保险股份有限公司 | Automatically generate method, electronic device and the readable storage medium storing program for executing of minutes |
| CN109166578A (en) * | 2018-08-14 | 2019-01-08 | Oppo广东移动通信有限公司 | Mobile terminal, sound control method and Related product |
| CN109388701A (en) * | 2018-08-17 | 2019-02-26 | 深圳壹账通智能科技有限公司 | Minutes generation method, device, equipment and computer storage medium |
-
2019
- 2019-04-22 CN CN201910322936.9A patent/CN110033768A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1291112A (en) * | 1998-12-24 | 2001-04-11 | 索尼公司 | Information processor, portable device, electronic pet device, recorded medium on which information processing procedure is recorded, and information processing method |
| CN1422424A (en) * | 2000-03-02 | 2003-06-04 | 雅马哈株式会社 | Telephone terminal |
| CN201490318U (en) * | 2009-04-27 | 2010-05-26 | 中兴通讯股份有限公司 | Mobile phone and rod antenna |
| CN201838706U (en) * | 2010-10-15 | 2011-05-18 | 福建星海通信科技有限公司 | Telescopic antenna |
| CN105228434A (en) * | 2015-08-13 | 2016-01-06 | 诸爱道 | Security terminal machine |
| CN105789813A (en) * | 2016-03-23 | 2016-07-20 | 广东丰光科技有限公司 | Expansion antenna device |
| CN106919561A (en) * | 2017-04-25 | 2017-07-04 | 安徽声讯信息技术有限公司 | Intelligent meeting stenographic machine |
| CN107221331A (en) * | 2017-06-05 | 2017-09-29 | 深圳市讯联智付网络有限公司 | A kind of personal identification method and equipment based on vocal print |
| CN108399923A (en) * | 2018-02-01 | 2018-08-14 | 深圳市鹰硕技术有限公司 | More human hairs call the turn spokesman's recognition methods and device |
| CN208027740U (en) * | 2018-04-24 | 2018-10-30 | 郑州小蝌蚪文化传播有限公司 | A kind of portable intelligent sound identification device |
| CN108986826A (en) * | 2018-08-14 | 2018-12-11 | 中国平安人寿保险股份有限公司 | Automatically generate method, electronic device and the readable storage medium storing program for executing of minutes |
| CN109166578A (en) * | 2018-08-14 | 2019-01-08 | Oppo广东移动通信有限公司 | Mobile terminal, sound control method and Related product |
| CN109388701A (en) * | 2018-08-17 | 2019-02-26 | 深圳壹账通智能科技有限公司 | Minutes generation method, device, equipment and computer storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110335612A (en) | Minutes generation method, device and storage medium based on speech recognition | |
| CN107767869A (en) | Method and apparatus for providing voice service | |
| CN108389578A (en) | Smart classroom speech control system | |
| CN103280011A (en) | Building entrance guard safety management system | |
| CN107210044A (en) | The modeling and reduction of UAV Propulsion System noise | |
| CN206282457U (en) | Teaching resource management system | |
| CN109600424A (en) | A kind of integrated mainframe micro, network insertion and audio collection classroom wisdom terminal | |
| CN109542233A (en) | A kind of lamp control system based on dynamic gesture and recognition of face | |
| CN110956965A (en) | Personalized intelligent home safety control system and method based on voiceprint recognition | |
| CN108334498A (en) | Method and apparatus for handling voice request | |
| CN109308901A (en) | Chanteur's recognition methods and device | |
| CN105933635A (en) | Method for attaching label to audio and video content | |
| CN1742322A (en) | Noise reduction and audio-visual speech activity detection | |
| CN110176250A (en) | It is a kind of based on the robust acoustics scene recognition method locally learnt | |
| CN113327619B (en) | Conference recording method and system based on cloud-edge collaborative architecture | |
| CN108877779A (en) | Method and apparatus for detecting voice tail point | |
| CN110033768A (en) | A kind of method and apparatus of intelligent search spokesman | |
| CN109413364A (en) | A kind of interactive remote meeting system and method | |
| CN109271896A (en) | A kind of student's evaluation system and method based on image recognition | |
| Cuccovillo et al. | Blind microphone analysis and stable tone phase analysis for audio tampering detection | |
| CN114666454A (en) | Intelligent conference system | |
| CN109785558A (en) | Door and window alarm method based on artificial intelligence | |
| CN115049970A (en) | Student classroom performance evaluation method based on multi-mode audio and video technology | |
| Wen | An Analysis of Emotional Responses of Students in Bilingual Classes and Adjustment Strategies. | |
| CN208985690U (en) | A kind of intelligence gate sentry |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190719 |